User | StevenZZH |
Upload Date | January 09 2025 06:20 AM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple M3 Pro |
System Information | |
---|---|
Operating System | macOS 15.3 (Build 24D5034f) |
Model | MacBook Pro (16-inch, Nov 2023) |
Model ID | Mac15,7 |
Motherboard | Mac15,7 |
CPU Information | |
---|---|
Name | Apple M3 Pro |
Topology | 1 Processor, 12 Cores |
Identifier | Apple M3 Pro |
Base Frequency | 4.05 GHz |
Cluster 1 | 6 Cores |
Cluster 2 | 6 Cores |
Memory Information | |
---|---|
Size | 18.00 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1553
288.8 IPS |
|
Image Classification (HP)
|
100% |
16334
3.04 KIPS |
|
Image Classification (Q)
|
97% |
19000
3.55 KIPS |
|
Image Segmentation (SP)
|
100% |
1927
31.2 IPS |
|
Image Segmentation (HP)
|
100% |
21544
349.2 IPS |
|
Image Segmentation (Q)
|
99% |
27033
438.2 IPS |
|
Pose Estimation (SP)
|
100% |
8759
10.2 IPS |
|
Pose Estimation (HP)
|
100% |
121805
142.1 IPS |
|
Pose Estimation (Q)
|
95% |
119072
139.6 IPS |
|
Object Detection (SP)
|
100% |
1780
141.2 IPS |
|
Object Detection (HP)
|
100% |
17489
1.39 KIPS |
|
Object Detection (Q)
|
91% |
20002
1.60 KIPS |
|
Face Detection (SP)
|
100% |
3593
42.7 IPS |
|
Face Detection (HP)
|
100% |
38004
451.6 IPS |
|
Face Detection (Q)
|
100% |
44676
530.8 IPS |
|
Depth Estimation (SP)
|
100% |
7080
54.5 IPS |
|
Depth Estimation (HP)
|
99% |
96784
745.7 IPS |
|
Depth Estimation (Q)
|
85% |
120308
940.6 IPS |
|
Style Transfer (SP)
|
100% |
21572
27.7 IPS |
|
Style Transfer (HP)
|
100% |
225332
289.7 IPS |
|
Style Transfer (Q)
|
96% |
210380
271.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
5189
191.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
44966
1.66 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54640
2.02 KIPS |
|
Text Classification (SP)
|
100% |
2762
3.69 KIPS |
|
Text Classification (HP)
|
100% |
4800
6.41 KIPS |
|
Text Classification (Q)
|
93% |
4746
6.37 KIPS |
|
Machine Translation (SP)
|
100% |
3513
60.5 IPS |
|
Machine Translation (HP)
|
100% |
4521
77.9 IPS |
|
Machine Translation (Q)
|
98% |
4657
80.5 IPS |